CN105225661B - Sound control method and system - Google Patents
Sound control method and system Download PDFInfo
- Publication number
- CN105225661B CN105225661B CN201410234794.8A CN201410234794A CN105225661B CN 105225661 B CN105225661 B CN 105225661B CN 201410234794 A CN201410234794 A CN 201410234794A CN 105225661 B CN105225661 B CN 105225661B
- Authority
- CN
- China
- Prior art keywords
- audio signal
- environmental noise
- controlled terminal
- mark
- audio
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The present invention relates to a kind of sound control method and systems, this method picks up the audio signal that noise equipment generates using environmental noise pick device, and it is audio number by the audio-frequency signal coding of pickup and is sent to controlled terminal, controlled terminal is when detecting the first audio signal, the voice data currently detected is converted into the second audio signal, and the first audio signal is compared with second audio signal, reject the part in first audio signal with second audio signals match, generate phonetic control command, respond the phonetic control command of the generation, the second audio signal by that will receive the generation of the noise equipment in the first audio signal is rejected, improve the accuracy of voice control.
Description
Technical field
The present invention relates to voice control technology field more particularly to a kind of sound control methods and device.
Background technique
With the development of speech recognition technology, more and more equipment are controlled using voice, main using controlled at present
Voice pick device built in equipment, the voice pick device pick up the phonetic control command that user sends and identification, were identifying
According to the mapping relations between preset phonetic control command and control routine in journey, the phonetic control command received is determined
Corresponding control routine responds the voice control that the control routine realizes controlled terminal.
In the prior art, there may be sound equipment (such as television sets and radio reception in environment locating for general controlled terminal
Machine lamp), then it, may in the phonetic control command that controlled terminal receives when user sends phonetic control command to controlled terminal
The noise data played including sound equipment leads to voice control accuracy rate so that mistake occurs in the identification of phonetic control command
It is low.
Summary of the invention
The main object of the present invention is to provide a kind of sound control method and device, it is intended to improve the accurate of voice control
Property.
The present invention proposes a kind of sound control method, comprising:
Controlled terminal is in real time or the voice data that environmental noise pick device is sent is detected in timing, wherein the environment is made an uproar
Sound pick device picks up the audio signal that noise equipment generates, and the audio signal based on pickup generates voice data；
It is described when detecting the first audio signal and detecting the voice data of the environmental noise pick device transmission
The voice data currently detected is converted to the second audio signal by controlled terminal；
The controlled terminal rejects the part in first audio signal with second audio signals match, to generate
Phonetic control command；
The controlled terminal responds the phonetic control command of the generation.
Preferably, the controlled terminal rejects the portion in first audio signal with second audio signals match
Point, to generate phonetic control command the step of includes:
The controlled terminal adjusts second audio signal according to preset dampening information；
Second audio signal after adjusting is compared the controlled terminal with first audio signal；
The controlled terminal rejects the portion in first audio signal with second audio signals match after adjusting
Point, and generate phonetic control command.
Preferably, the controlled terminal includes: according to the step of preset dampening information adjusting second audio signal
The controlled terminal according to the voice data received determine corresponding environmental noise pick device mark or
Person's noise equipment mark；
The controlled terminal is identified according to preset dampening information and environmental noise pick device or noise equipment identifies
Between mapping relations, obtain determining environmental noise pick device mark or the corresponding decaying letter of noise equipment mark
Breath；
The controlled terminal adjusts corresponding second audio signal according to the dampening information got.
Preferably, the controlled terminal detecting real-time and receive environmental noise pick device transmission voice data the step of
Before, this method further include:
When detecting the audio play instruction of noise equipment transmission, the controlled terminal is played based on the audio received
Instruction determines the play time and strength information of audio signal to be played；
Receive noise equipment broadcasting third audio signal when, obtain the third audio signal strength information,
The receiving time of the third audio signal and the mark of noise equipment or the environment for receiving the third audio signal are made an uproar
The mark of sound pick device；
The receiving time of strength information and the audio signal based on the third audio signal, and determine wait broadcast
The play time and strength information for putting audio signal, generate corresponding dampening information；
The dampening information of generation is associated with guarantor with the mark of the mark of the noise equipment or environmental noise pick device
It deposits.
Preferably, the controlled terminal is in real time or the voice data that environmental noise pick device is sent is detected in timing, wherein
The environmental noise pick device picks up the audio signal that noise equipment generates, and the audio signal based on pickup generates voice number
According to the step of after, this method comprises:
When detecting first audio signal, and the voice number of environmental noise pick device transmission is not received currently
According to when, the controlled terminal responds first audio signal.
The present invention also proposes a kind of speech control system, comprising:
Detecting module, the voice data sent for detecting real-time environmental noise pick device, wherein the environmental noise
Pick device picks up the audio signal that noise equipment generates, and the audio signal based on pickup generates voice data；
Conversion module, for detecting the first audio signal and detecting the language that the environmental noise pick device sends
When sound data, the voice data currently detected is converted into the second audio signal；
Processing module is used in controlled terminal rejecting first audio signal and second audio signals match
Part, to generate phonetic control command；
Respond module, for responding the phonetic control command of the generation.
Preferably, the processing module includes:
Unit is adjusted, for adjusting second audio signal according to preset dampening information；
The second audio signal after adjusting is compared comparing unit with first audio signal；
Processing unit, for rejecting the portion in first audio signal with second audio signals match after adjusting
Point, and generate new phonetic control command.
Preferably, the adjusting unit includes:
Subelement is determined, for determining corresponding environmental noise pick device mark according to the data received；
Subelement is obtained, according to the mapping relations between preset dampening information and environmental noise pick device mark, is obtained
Determining environmental noise pick device is taken to identify corresponding dampening information；
Regulator unit, for adjusting corresponding second audio signal according to the dampening information got.
Preferably, the system further include:
Determining module, for being broadcast based on the audio received when detecting the audio play instruction of noise equipment transmission
Put play time and strength information that instruction determines audio signal to be played；
Module is obtained, for obtaining the audio signal received when receiving the audio signal of noise equipment broadcasting
The environment of strength information, the mark of the receiving time of the audio signal and noise equipment or the reception third audio signal
The mark of noise pickup device；
Generation module, when reception for the strength information based on the audio signal received and the audio signal
Between, and the play time and strength information of determining audio signal to be played, generate corresponding dampening information；
Memory module, the mark or environmental noise pick device of dampening information and the noise equipment for that will generate
Mark be associated with save.
Preferably, the respond module is also used to detecting first audio signal, and does not receive environment currently
When the voice data that noise pickup device is sent, first audio signal detected is responded.
Sound control method proposed by the present invention and system, this method pick up noise equipment using environmental noise pick device
The audio signal of generation, and be audio number by the audio-frequency signal coding of pickup and be sent to controlled terminal, controlled terminal is being detected
When to the first audio signal, the voice data currently detected is converted into the second audio signal, and by the first audio signal with
Second audio signal is compared, and rejects the part in first audio signal with second audio signals match, raw
The phonetic control command of Cheng Xin responds the phonetic control command of the generation, by that will receive the noise in the first audio signal
The second audio signal that equipment generates is rejected, and the accuracy of voice control is improved.
Detailed description of the invention
Fig. 1 is the hardware structural diagram of the preferred embodiment for the controlled terminal that the present invention realizes voice control；
Fig. 2 is the functional block diagram of speech control system preferred embodiment in Fig. 1；
Fig. 3 is the flow diagram of sound control method preferred embodiment of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
With reference to the accompanying drawing and specific embodiment is described further with regard to technical solution of the present invention.It should be appreciated that this
Locate described specific embodiment to be only used to explain the present invention, be not intended to limit the present invention.
Referring to Fig.1, Fig. 1 is the hardware configuration signal of the preferred embodiment for the controlled terminal that the present invention realizes voice control
Figure.
The controlled terminal 1 includes processing unit 11, storage unit 12, receiving unit 13, voice pick device 14 and voice
Control system 15.The controlled terminal 1 can be the terminal of the achievable voice controls such as air conditioner and television set.
Voice pick device 14, in the vibration for receiving sound wave, the electric signal that vibration generates to be converted to audio
Signal.
Storage unit 12, for store the speech control system 15 and its operation data and phonetic control command and
Mapping relations between control routine.It is emphasized that the storage unit 12 is either an individual storage device,
It can be the general designation of multiple and different storage devices, therefore not to repeat here.
Receiving unit 13, under the control of processing unit 11, the audio data that detecting environmental noise equipment is sent should
Receiving unit 13 can be WIFI module, infrared signal transmission unit, bluetooth module, the wireless signal transmitter with transmitting antenna
Or any other applicable wireless signal receiving unit 13 (the preferred WIFI module of the present embodiment).
The processing unit 11, for calling and executing the speech control system 15, control receiving unit 13 is in real time or timing
The voice data of environmental noise pick device transmission is detected and received, while controlling voice pick device 14 and detecting and receive first
The voice data that receiving unit 13 receives is converted to the second audio letter when receiving the first audio signal by audio signal
Number, and first audio signal is compared with second audio signal, reject in first audio signal with institute
The part of the second audio signals match is stated, phonetic control command is generated, calls the phonetic control command stored in storage unit 12
Mapping relations between control routine determine control routine corresponding to the phonetic control command generated, and executing should
Control routine.The processing unit 11 and storage unit 12 both can be individual unit respectively, also can integrate together, constitute
One controller, therefore not to repeat here.
It is the functional block diagram of speech control system preferred embodiment in Fig. 1 referring to Fig. 2, Fig. 2.
It is emphasized that it will be apparent to those skilled in the art that functional block diagram shown in Fig. 2 is only one preferably real
The exemplary diagram of example is applied, those skilled in the art surrounds the functional module of speech control system 15 shown in Fig. 2, can carry out easily
The supplement of new functional module；The title of each functional module is self-defined title, is only used for auxiliary and understands the speech control system
15 each program function block is not used in restriction technical solution of the present invention, and the core of technical solution of the present invention is, each customized
The function to be reached of the functional module of title.
The present embodiment proposes a kind of speech control system 15, comprising:
Detecting module 151, the voice data sent for timing or detecting real-time environmental noise pick device, wherein institute
It states environmental noise pick device and picks up the audio signal that noise equipment generates, and the audio signal based on pickup generates voice number
According to；
In the present embodiment, environmental noise pick device is set to the model that can receive the audio signal of noise equipment broadcasting
In enclosing, preferred embodiment is that environmental noise pick device is set near the loudspeaker of noise equipment, interference is reduced, so that receiving
Audio signal is more accurate.The environmental noise pick device is preferably shotgun microphone, and only directional reception noise equipment is raised
The audio signal that sound device plays.
When detecting module 151 generates audio data based on the audio signal of pickup, it can directly be picked up and be filled according to environmental noise
The communication protocol installed between controlled terminal encodes the audio signal of pickup, generates corresponding audio data.Example
Such as, when the communication mode between environmental noise pick device and controlled terminal is that WIFI is communicated, corresponding communication protocol is
WIFI communication protocol then encodes the audio signal picked up using WIFI communication protocol.
Conversion module 152, for detect the first audio signal and detect environmental noise pick device transmission language
When sound data, the voice data currently detected is converted into the second audio signal；
Similarly, conversion module 152 is communicated when receiving voice data using between the setting of noise pickup device
Communication protocol parse the voice data received, voice data is resolved into the second audio signal.
It will be appreciated by persons skilled in the art that can be arranged in controlled terminal a variety of detecting modules such as WIFI module with
And the wireless sensings such as infrared module module or the wireline interfaces such as RS485 interface and serial line interface receive environmental noise and pick up
The voice data that device is sent, conversion module 152 can be when detecting module 151 receive voice data, and determination receives voice
The interface of data perhaps communication protocol corresponding to interface or module of the module using the determination to the voice data received
It is decoded, the voice data received is converted into the second audio signal.
Processing module 153, for rejecting the part in first audio signal with second audio signals match, with
Generate phonetic control command；
The first audio signal that voice pick device in controlled terminal receives includes that the voice control of user's transmission refers to
Order and environmental noise (such as the second audio signal).
In the present embodiment, processing module 153 reject in first audio signal with second audio signals match
Part when can waveform compare by way of realize, as compare the first audio signal and convert after the second audio signal
Waveform trend, the amplitude of the waveform according to corresponding to audio controls adjust waveform corresponding to the first audio signal
Section.
Respond module 154, for responding the phonetic control command of the generation.
In the present embodiment, respond module 154 is when responding the phonetic control command of the generation, the voice control that can will prestore
System instruction is compared with the phonetic control command in the mapping relations between control routine with the phonetic control command of the generation,
The determining and mapping relations between the matched phonetic control command of phonetic control command and control routine of the generation, according to this
Mapping relations between the phonetic control command matched and control routine determine control corresponding to the phonetic control command of the generation
Code executes the control routine.When the phonetic control command of generation is compared with the phonetic control command prestored, if crucial
The quantity of sound matching or matched key sound is greater than preset threshold values, then it is assumed that the phonetic control command of generation and the language prestored
Sound control instructions match.
The speech control system that the present embodiment proposes, the system are picked up noise equipment using environmental noise pick device and are generated
Audio signal, and be audio number by the audio-frequency signal coding of pickup and be sent to controlled terminal, controlled terminal is detecting the
When one audio signal, the voice data currently detected is converted into the second audio signal, and by the first audio signal and this
Two audio signals are compared, and reject the part in first audio signal with second audio signals match, generate new
Phonetic control command, the phonetic control command of the generation is responded, by the way that the noise equipment in the first audio signal will be received
The second audio signal generated is rejected, and the accuracy of voice control is improved.
It further, is the accuracy for improving voice control, the processing module 153 includes:
Unit 1531 is adjusted, for adjusting second audio signal according to preset dampening information；
The second audio signal after adjusting is compared comparing unit 1532 with first audio signal；
Processing unit 1533, for rejecting the part in first audio signal with second audio signals match,
And generate phonetic control command.
It will appear decaying during being sent to controlled terminal by noise equipment due to audio signal, which includes
The attenuation amplitude and delay duration of audio signal, since the location of noise equipment is constant, therefore attenuation amplitude and delay
Duration is constant, therefore default attenuation amplitude and delay duration, and according to preset attenuation amplitude and delay duration to the second sound
The waveform of frequency signal is adjusted, and waveform adjusted is compared with the waveform of the first audio signal received.
It further, is the accuracy for improving voice control, the adjusting unit 1531 includes:
Subelement is determined, for determining corresponding environmental noise pick device mark according to the voice data received or making an uproar
Sound device identification；
Subelement is obtained, according between preset dampening information and environmental noise pick device mark or noise equipment mark
Mapping relations, obtain determining environmental noise pick device mark or the corresponding dampening information of noise equipment mark；
Regulator unit, for adjusting corresponding second audio signal according to the dampening information got.
In the present embodiment, there may be multiple noise equipments in environment locating for controlled device, such as in controlled device
When for air conditioner, indoor television set and radio etc. can cause to do as noise equipment to the voice control of air conditioner
It disturbs, therefore needs that environmental noise pick device is arranged at the loudspeaker of each noise equipment, and save and preset in controlled terminal
Dampening information and environmental noise pick device mark or noise equipment mark between mapping relations.
It will be appreciated by persons skilled in the art that when being provided with multiple environmental noise pick devices, detecting module 151
The voice data that multiple environmental noise pick devices are sent may be received simultaneously, therefore to identify different environmental noise device hairs
The voice data sent, environmental noise pick device can add environmental noise pickup when sending voice data in voice data
The noise equipment of noise equipment corresponding to device identification or environmental noise pick device identifies, and determines subelement according to detecing
It surveys the voice data that module 151 receives and determines corresponding environmental noise pick device mark or noise equipment mark, obtain son
Unit is obtained according to the mapping relations between preset dampening information and environmental noise pick device mark or noise equipment mark
Determining environmental noise pick device mark or the corresponding dampening information of noise equipment mark, regulator unit is according to getting
Dampening information adjust corresponding second audio signal, guarantee the accuracy for carrying out Attenuation adjustable to the second audio signal, that is, mention
The accuracy of high voice control.
It further, is the accuracy for improving voice control, the system further include:
Determining module, for being broadcast based on the audio received when detecting the audio play instruction of noise equipment transmission
Put play time and strength information that instruction determines third audio signal to be played；
Module is obtained, for obtaining the institute received when receiving the third audio signal of noise equipment broadcasting
It states strength information, the receiving time of the third audio signal and the mark of noise equipment of third audio signal or receives institute
State the mark of the environmental noise pick device of third audio signal；
Generation module, for strength information and third audio letter based on the third audio signal received
Number receiving time, and the play time and strength information of the third audio signal to be played that determine are generated and corresponding are declined
Subtract information；
Memory module, the mark or environmental noise pick device of dampening information and the noise equipment for that will generate
Mark be associated with save.
In the present embodiment, the can be determined when controlled terminal only receives the third audio signal of noise equipment broadcasting
The dampening information of three audio signals.Noise equipment can be by sending third sound in the forward direction controlled terminal for playing third audio signal
Frequency signal play time and strength information, so that controlled terminal determines the play time of third audio signal received and strong
Information is spent, it can also be a time interval which can play for a time point such as 8:00, as played after 5min,
When the play time received is time interval, controlled terminal is based on receiving the play time interval time point with timely
Between be spaced, determine the play time of third audio signal.
It will be appreciated by persons skilled in the art that noise equipment can also be after playing third audio signal, to controlled end
End sends play time and strength information, strength information of the generation module based on the third audio signal received and should
The receiving time of third audio signal, and the play time and strength information of determining third audio signal to be played, it is raw
At corresponding dampening information, memory module picks up the mark or environmental noise of the dampening information of generation and the noise equipment
The mark of device, which is associated with, to be saved.
Further, to improve voice control efficiency, the respond module 156 is also used to detecting the first audio letter
Number, and when the current voice data for not receiving the transmission of environmental noise pick device, respond the first audio signal received.
It will be appreciated by persons skilled in the art that detecting the first audio letter to improve the accuracy rate of voice control
Number, and when the current voice data for not receiving the transmission of environmental noise pick device, the vocal print that can extract the first audio signal is special
Sign, and the vocal print feature of extraction is compared with preset vocal print feature, it is special in the vocal print feature of extraction and preset vocal print
When sign matching, first audio signal received is responded.
It is the flow diagram of sound control method preferred embodiment of the present invention referring to Fig. 3, Fig. 3.
The present embodiment proposes a kind of sound control method, comprising:
Step S10, controlled terminal is in real time or the voice data of environmental noise pick device transmission is detected and received in timing,
In, the environmental noise pick device picks up the audio signal that noise equipment generates, and the audio signal based on pickup generates language
Sound data；
In the present embodiment, environmental noise pick device is set to the model that can receive the audio signal of noise equipment broadcasting
In enclosing, preferred embodiment is that environmental noise pick device is set near the loudspeaker of noise equipment, interference is reduced, so that receiving
Audio signal is more accurate.The environmental noise pick device is preferably shotgun microphone, and only directional reception noise equipment is raised
The audio signal that sound device plays.
When controlled terminal generates audio data based on the audio signal of pickup, can directly it be set according to environmental noise pick device
The communication protocol set between controlled terminal encodes the audio signal of pickup, generates corresponding audio data.For example, ring
When communication mode between border noise pickup device and controlled terminal is that WIFI is communicated, corresponding communication protocol is WIFI communication
Agreement then encodes the audio signal picked up using WIFI communication protocol.
Step S20, when detecting the first audio signal, the controlled terminal converts the voice data currently detected
For the second audio signal；
Similarly, controlled terminal is when receiving voice data, using what is communicated between the setting of noise pickup device
Communication protocol parses the voice data received, and voice data is resolved to the second audio signal.
It will be appreciated by persons skilled in the art that can be arranged in controlled terminal a variety of detecting modules such as WIFI module with
And the wireless sensings such as infrared module module or the wireline interfaces such as RS425 interface and serial line interface receive environmental noise and pick up
Device send voice data, controlled terminal can when receiving voice data, determine receive voice data interface or
Module, communication protocol corresponding to the interface or module using the determination are decoded the voice data received, will
The voice data received is converted to the second audio signal.
Step S30, the controlled terminal reject the portion in first audio signal with second audio signals match
Point, to generate new phonetic control command；
The first audio signal that voice pick device in controlled terminal receives includes that the voice control of user's transmission refers to
Order and environmental noise (such as the second audio signal).In the present embodiment, controlled terminal reject in first audio signal with
It can be realized in such a way that waveform compares when the part of second audio signals match, such as compare the first audio signal and turn
The waveform of the second audio signal after changing moves towards, and the amplitude of the waveform according to corresponding to audio controls is to the first audio signal
Corresponding waveform is adjusted.
Step S40, the controlled terminal respond the phonetic control command of the generation.
In the present embodiment, controlled terminal is when responding the phonetic control command of the generation, the voice control that can will prestore
Instruction is compared with the phonetic control command in the mapping relations between control routine with the phonetic control command of the generation, really
The fixed mapping relations between the matched phonetic control command of phonetic control command and control routine of the generation, according to the matching
Phonetic control command and control routine between mapping relations, determine control generation corresponding to the phonetic control command of the generation
Code, executes the control routine.When the phonetic control command of generation is compared with the phonetic control command prestored, if key sound
The quantity of matching or matched key sound is greater than preset threshold values, then it is assumed that the phonetic control command of generation and the voice prestored
Control instruction matching.
The sound control method that the present embodiment proposes, this method are picked up noise equipment using environmental noise pick device and are generated
Audio signal, and be audio number by the audio-frequency signal coding of pickup and be sent to controlled terminal, controlled terminal is detecting the
When one audio signal, the voice data currently detected is converted into the second audio signal, and by the first audio signal and this
Two audio signals are compared, and reject the part in first audio signal with second audio signals match, generate new
Phonetic control command, the phonetic control command of the generation is responded, by the way that the noise equipment in the first audio signal will be received
The second audio signal generated is rejected, and the accuracy of voice control is improved.
It further, is the accuracy for improving voice control, the step S30 includes:
Step S31, the controlled terminal adjust second audio signal according to preset dampening information；
The second audio signal after adjusting is compared with first audio signal for step S32, the controlled terminal；
Step S33, the controlled terminal reject in first audio signal with second audio signal after adjusting
Matched part, and generate phonetic control command.
It will appear decaying during being sent to controlled terminal by noise equipment due to the second audio signal, the dampening information
Attenuation amplitude and delay duration including the second audio signal, since the location of noise equipment is constant, therefore attenuation amplitude
And delay duration is constant, therefore default attenuation amplitude and delay duration, and according to preset attenuation amplitude and delay duration
The waveform of second audio signal is adjusted, and waveform adjusted and the waveform of the first audio signal received are carried out
It compares.
It further, is the accuracy for improving voice control, the step S31 includes:
The controlled terminal determines that corresponding environmental noise pick device identifies or makes an uproar according to the voice data received
Sound device identification；
The controlled terminal is identified according to preset dampening information and environmental noise pick device or noise equipment identifies
Between mapping relations, obtain determining environmental noise pick device mark or the corresponding decaying letter of noise equipment mark
Breath；
The controlled terminal adjusts corresponding second audio signal according to the dampening information got.
In the present embodiment, there may be multiple noise equipments in environment locating for controlled device, such as in controlled device
When for air conditioner, indoor television set and radio etc. can cause to do as noise equipment to the voice control of air conditioner
It disturbs, therefore needs that environmental noise pick device is arranged at the loudspeaker of each noise equipment, and save and preset in controlled terminal
Dampening information and environmental noise pick device mark or noise equipment mark between mapping relations.
It will be appreciated by persons skilled in the art that controlled terminal can when being provided with multiple environmental noise pick devices
The voice data that multiple environmental noise pick devices are sent can be received simultaneously, therefore to identify that different environmental noise devices is sent
Voice data, environmental noise pick device when sending voice data, can in voice data environment noise pickup device mark
The noise equipment mark of noise equipment corresponding to knowledge or environmental noise pick device, controlled terminal is according to the language received
Sound data determine corresponding environmental noise pick device mark or noise equipment mark, and according to preset dampening information and environment
Mapping relations between noise pickup device identification or noise equipment mark, obtain determining environmental noise pick device mark or
The corresponding dampening information of noise equipment mark, controlled terminal, which adjusts corresponding second audio according to the dampening information got, to be believed
Number, guarantee the accuracy for carrying out Attenuation adjustable to the second audio signal, that is, improves the accuracy of voice control.
It further, is the accuracy for improving voice control, before step S10, this method comprises:
When detecting the audio play instruction of noise equipment transmission, the controlled terminal is played based on the audio received
Instruction determines the play time and strength information of third audio signal to be played；
When receiving the third audio signal of noise equipment broadcasting, the third audio signal received is obtained
Strength information, the receiving time of the third audio signal and the mark of noise equipment or receive the third audio signal
Environmental noise pick device mark；
The receiving time of strength information and the third audio signal based on the third audio signal received, and
The play time and strength information of determining third audio signal to be played, generate corresponding dampening information；
The dampening information of generation is associated with guarantor with the mark of the mark of the noise equipment or environmental noise pick device
It deposits.
In the present embodiment, the can be determined when controlled terminal only receives the third audio signal of noise equipment broadcasting
The dampening information of three audio signals.Noise equipment can be by sending third sound in the forward direction controlled terminal for playing third audio signal
Frequency signal play time and strength information, so that controlled terminal determines the play time of third audio signal received and strong
Information is spent, it can also be a time interval which can play for a time point such as 8:00, as played after 5min,
When the play time received is time interval, controlled terminal is based on receiving the play time interval time point with timely
Between be spaced, determine the play time of third audio signal.
It will be appreciated by persons skilled in the art that noise equipment can also be after playing third audio signal, to controlled end
End sends play time and strength information, strength information of the controlled terminal based on the third audio signal received and should
The receiving time of third audio signal, and the play time and strength information of determining third audio signal to be played, it is raw
At corresponding dampening information, and by the mark of the dampening information of generation and the noise equipment or environmental noise pick device
Mark association saves.
Further, it is raising voice control efficiency, after step S10, the method comprising the steps of:
When detecting the first audio signal, and not receiving the voice data of environmental noise pick device transmission currently,
The controlled terminal responds the first audio signal received.
It will be appreciated by persons skilled in the art that detecting the first audio letter to improve the accuracy rate of voice control
Number, and when the current voice data for not receiving the transmission of environmental noise pick device, controlled terminal can extract the first audio signal
Vocal print feature, and the vocal print feature of extraction is compared with preset vocal print feature, in the vocal print feature of extraction and default
Vocal print feature matching when, respond first audio signal received.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.Pass through above embodiment party
The description of formula, it is required general that those skilled in the art can be understood that above-described embodiment method can add by software
The mode of hardware platform is realized, naturally it is also possible to which by hardware, but in many cases, the former is more preferably embodiment.It is based on
Such understanding, substantially the part that contributes to existing technology can be with software product in other words for technical solution of the present invention
Form embody, which is stored in a storage medium (such as ROM/RAM, magnetic disk, CD), including
Some instructions are used so that a terminal device (can be mobile phone, computer, server or the network equipment etc.) executes this hair
Method described in bright each embodiment.
The above description is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all utilizations
Equivalent structure transformation made by description of the invention and accompanying drawing content is applied directly or indirectly in other relevant technology necks
Domain is included within the scope of the present invention.
Claims (10)
1. a kind of sound control method characterized by comprising
Controlled terminal is in real time or the voice data that environmental noise pick device is sent is detected in timing, wherein the environmental noise picks up
Device is taken to pick up the audio signal that noise equipment generates, and the audio signal based on pickup generates voice data；
It is described controlled when detecting the first audio signal and detecting the voice data of the environmental noise pick device transmission
The voice data currently detected is converted to the second audio signal by terminal；
The controlled terminal reject in first audio signal with carry out dampening information adjusting after the second audio signals match
Part, to generate phonetic control command；
The controlled terminal responds the phonetic control command of the generation.
2. the method according to claim 1, wherein the controlled terminal reject in first audio signal with
The part of second audio signals match, to generate phonetic control command the step of include:
The controlled terminal adjusts second audio signal according to preset dampening information；
Second audio signal after adjusting is compared the controlled terminal with first audio signal；
The controlled terminal rejects the part in first audio signal with second audio signals match after adjusting, and
Generate phonetic control command.
3. according to the method described in claim 2, it is characterized in that, the controlled terminal adjusts institute according to preset dampening information
The step of stating the second audio signal include:
The controlled terminal determines that corresponding environmental noise pick device identifies or makes an uproar according to the voice data received
Sound device identification；
The controlled terminal is according between preset dampening information and environmental noise pick device mark or noise equipment mark
Mapping relations, obtain determining environmental noise pick device mark or the corresponding dampening information of noise equipment mark；
The controlled terminal adjusts corresponding second audio signal according to the dampening information got.
4. the method according to claim 1, wherein the controlled terminal detecting real-time and receiving environmental noise and picking up
Before the step of voice data for taking device to send, this method further include:
When detecting the audio play instruction of noise equipment transmission, the controlled terminal is based on the audio play instruction received
Determine the play time and strength information of audio signal to be played；
When receiving the third audio signal of noise equipment broadcasting, the strength information, described of the third audio signal is obtained
The receiving time of third audio signal and the mark of noise equipment or the environmental noise for receiving the third audio signal pick up
Take the mark of device；
The receiving time of strength information and the audio signal based on the third audio signal, and the sound to be played determined
The play time and strength information of frequency signal, generate corresponding dampening information；
The dampening information of generation is associated with preservation with the mark of the mark of the noise equipment or environmental noise pick device.
5. the method according to claim 1, wherein detecting environmental noise picks up the controlled terminal in real time or periodically
The voice data for taking device to send, wherein the environmental noise pick device picks up the audio signal that noise equipment generates, and base
After the step of audio signal of pickup generates voice data, this method comprises:
When detecting first audio signal, and the voice data of environmental noise pick device transmission is not received currently
When, the controlled terminal responds first audio signal.
6. a kind of speech control system characterized by comprising
Detecting module, the voice data sent for detecting real-time environmental noise pick device, wherein the environmental noise picks up
Device picks up the audio signal that noise equipment generates, and the audio signal based on pickup generates voice data；
Conversion module, for detecting the first audio signal and detecting the voice number that the environmental noise pick device sends
According to when, the voice data currently detected is converted into the second audio signal；
Processing module, for reject in first audio signal with carry out dampening information adjusting after the second audio signals match
Part, to generate phonetic control command；
Respond module, for responding the phonetic control command of the generation.
7. system according to claim 6, which is characterized in that the processing module includes:
Unit is adjusted, for adjusting second audio signal according to preset dampening information；
The second audio signal after adjusting is compared comparing unit with first audio signal；
Processing unit, for rejecting the part in first audio signal with second audio signals match after adjusting,
And generate new phonetic control command.
8. system according to claim 7, which is characterized in that the adjusting unit includes:
Subelement is determined, for determining corresponding environmental noise pick device mark according to the data received；
Subelement is obtained, according to the mapping relations between preset dampening information and environmental noise pick device mark, is obtained true
The corresponding dampening information of fixed environmental noise pick device mark；
Regulator unit, for adjusting corresponding second audio signal according to the dampening information got.
9. system according to claim 6, which is characterized in that the system further include:
Determining module, for being referred to based on the audio broadcasting received when detecting the audio play instruction of noise equipment transmission
Enable the play time and strength information for determining audio signal to be played；
Module is obtained, for obtaining the third sound received when receiving the third audio signal of noise equipment broadcasting
The strength information of frequency signal, the mark of the receiving time of the third audio signal and noise equipment or the reception third
The mark of the environmental noise pick device of audio signal；
Generation module, the reception for strength information and the audio signal based on the third audio signal received
Time, and the play time and strength information of determining audio signal to be played, generate corresponding dampening information；
Memory module, dampening information and the mark of the noise equipment or the mark of environmental noise pick device for that will generate
Know association to save.
10. system according to claim 6, which is characterized in that the respond module is also used to detecting described first
Audio signal, and when the current voice data for not receiving the transmission of environmental noise pick device, respond described first detected
Audio signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410234794.8A CN105225661B (en) | 2014-05-29 | 2014-05-29 | Sound control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410234794.8A CN105225661B (en) | 2014-05-29 | 2014-05-29 | Sound control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105225661A CN105225661A (en) | 2016-01-06 |
| CN105225661B true CN105225661B (en) | 2019-06-28 |
Family
ID=54994571
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410234794.8A Active CN105225661B (en) | 2014-05-29 | 2014-05-29 | Sound control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105225661B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109389976A (en) * | 2018-09-27 | 2019-02-26 | 珠海格力电器股份有限公司 | Intelligent appliance apparatus control method, device, intelligent appliance equipment and storage medium |
| WO2020220345A1 (en) * | 2019-04-30 | 2020-11-05 | 华为技术有限公司 | Voice command recognition method and apparatus |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102890936A (en) * | 2011-07-19 | 2013-01-23 | 联想(北京)有限公司 | Audio processing method and terminal device and system |
| CN102915732A (en) * | 2012-10-31 | 2013-02-06 | 黑龙江省电力有限公司信息通信分公司 | Method and device for identifying voice commands restraining background broadcasts |
| CN103050116A (en) * | 2012-12-25 | 2013-04-17 | 安徽科大讯飞信息科技股份有限公司 | Voice command identification method and system |
| CN103559878A (en) * | 2013-09-04 | 2014-02-05 | 张家港保税区润桐电子技术研发有限公司 | Method for eliminating noise in audio information and device thereof |
| CN103597542A (en) * | 2011-06-03 | 2014-02-19 | 美国思睿逻辑有限公司 | An adaptive noise canceling architecture for a personal audio device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8831936B2 (en) * | 2008-05-29 | 2014-09-09 | Qualcomm Incorporated | Systems, methods, apparatus, and computer program products for speech signal processing using spectral contrast enhancement |
-
2014
- 2014-05-29 CN CN201410234794.8A patent/CN105225661B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103597542A (en) * | 2011-06-03 | 2014-02-19 | 美国思睿逻辑有限公司 | An adaptive noise canceling architecture for a personal audio device |
| CN102890936A (en) * | 2011-07-19 | 2013-01-23 | 联想(北京)有限公司 | Audio processing method and terminal device and system |
| CN102915732A (en) * | 2012-10-31 | 2013-02-06 | 黑龙江省电力有限公司信息通信分公司 | Method and device for identifying voice commands restraining background broadcasts |
| CN103050116A (en) * | 2012-12-25 | 2013-04-17 | 安徽科大讯飞信息科技股份有限公司 | Voice command identification method and system |
| CN103559878A (en) * | 2013-09-04 | 2014-02-05 | 张家港保税区润桐电子技术研发有限公司 | Method for eliminating noise in audio information and device thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105225661A (en) | 2016-01-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106898348B (en) | Dereverberation control method and device for sound production equipment | |
| CN104185132B (en) | Channel configuration method, intelligent terminal and corresponding system | |
| CN106936987B (en) | Method and device capable of identifying voice source of Bluetooth headset | |
| CN108320749A (en) | Far field voice control device and far field speech control system | |
| US20090280800A1 (en) | Testing system and method for testing mobile phone | |
| CN102111314A (en) | Smart home voice control system and method based on Bluetooth transmission | |
| CN104978955A (en) | Voice control method and system | |
| CN104978956A (en) | Voice control method and system | |
| CN103944983A (en) | Error correction method and system for voice control instruction | |
| CN110767225B (en) | Voice interaction method, device and system | |
| CN103686338A (en) | A method for processing audio data, an apparatus thereof and a television set | |
| CN105225661B (en) | Sound control method and system | |
| CN104180473A (en) | Wind direction switching method and system for air conditioner | |
| CN109121059A (en) | Loudspeaker plug-hole detection method and Related product | |
| CN103916511A (en) | Information processing method and electronic equipment | |
| CN110728969A (en) | Double-point sounding karaoke system and method | |
| CN105407445B (en) | A kind of connection method and the first electronic equipment | |
| CN107977187B (en) | Reverberation adjusting method and electronic equipment | |
| CN106409306A (en) | Intelligent system obtaining human voice and obtaining method based on the system | |
| CN102322928B (en) | Electronic scale, mobile equipment, body weight measuring system and wireless transmission method | |
| CN109102816A (en) | Coding control method, device and electronic equipment | |
| CN104202694A (en) | Method and system of orientation of voice pick-up device | |
| CN112712683A (en) | Control method and system of household appliance, remote controller and server | |
| CN109473096B (en) | Intelligent voice equipment and control method thereof | |
| CN105306685B (en) | The test method and mobile terminal of signal quality |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |